Methods for classifying a movement and movement classification system

Abstract

The invention relates to a method (100) for classifying a movement by means of a movement classification system (200) with a plurality of peripheral classification elements (201) and a central classification unit (203), wherein the peripheral classification elements (201) are arranged on different body parts (301) of a person (300) and each classify the movement of the person (300) based on sensor data, comprising: Receiving (101) classification data (205) of the plurality of peripheral classification elements (201) by the central classification unit (203), wherein the classification data (205) each comprise at least one peripheral classification value (207); Classifying (103) the movement and generating a classification value (209) by the central classification unit (203) based on the peripheral classification values ​​(207) of the plurality of peripheral classification elements (201); and Output (105) of the classification value (209) by the central classification unit (203) to a display unit (211). The invention further relates to a motion classification system (200).

Description

[0001] The present invention relates to a method for classifying a movement and a movement classification system. State of the art

[0002] Methods for classifying a movement are known from the prior art.

[0003] It is an object of the present invention to provide an improved method for classifying a motion and a motion classification system.

[0004] The problem is solved by the method for classifying a motion and the motion classification system of the independent claims. Advantageous embodiments are the subject of the dependent claims.

[0005] According to one aspect, a method for classifying a movement by a movement classification system with a plurality of peripheral classification elements and a central classification unit is provided, wherein the peripheral classification elements are arranged on different parts of the person's body and each classifies the person's movement based on sensor data, comprising: Receiving classification data from the majority of peripheral classification elements by the central classification unit, wherein the classification data each comprise at least one peripheral classification value; Classifying the movement and generating a classification value by the central classification unit based on the peripheral classification values ​​of the majority of peripheral classification elements; and Output of the classification value by the central classification unit to a display unit.

[0006] This allows for the technical advantage of providing an improved method for classifying motion. The method is implemented by a motion classification system comprising a plurality of peripheral classification elements and a central classification unit.

[0007] The multiple peripheral classification elements are positioned on body parts of a moving person and configured to classify their movement based on sensor readings. The central classification unit communicates with these peripheral classification elements and receives classification data from them. This data includes at least several peripheral classification values, each representing the movement classification performed by the respective peripheral classification element.

[0008] Based on the multiple peripheral classification values ​​of the multiple peripheral classification elements, the central classification unit creates a classification value for movement. The classification value for movement is thus based on the multiple peripheral classification values ​​of the individual peripheral classification elements. This allows for a higher degree of precision in classifying a person's movement.

[0009] By positioning the various peripheral classification elements at different locations on the person's body, multiple movements of individual body parts can be considered in the classification. This further improves the precision of the motion classification. The resulting classification value is then output to a display unit, allowing the user to view the corresponding motion classification of the person using the motion classification system.

[0010] According to one embodiment, the classification value determined by the central classification unit corresponds to one of the peripheral classification values ​​provided by the plurality of peripheral classification elements, if the respective peripheral classification value was provided by at least a predefined number of peripheral classification elements.

[0011] This allows for the technical advantage of greater precision in motion classification. The classification value generated by the central classification unit corresponds to the peripheral classification values ​​provided by the peripheral classification elements, provided a predefined number of these elements provide the same peripheral classification value.

[0012] According to one embodiment, the classification data each further comprise at least one motion value, wherein the method further comprises: determining a count of cyclic partial movements of the motion based on the motion values ​​of the plurality of peripheral classification elements by the central classification unit; and Output of the count value by the central classification unit to the display unit.

[0013] This allows for the technical advantage that, in addition to the classification value, a count of the cyclical partial movements of the person's movement can also be provided. The multiple peripheral classification elements provide movement values ​​alongside the peripheral classification values. The count generated by the central classification unit is based on the movement values ​​of the multiple peripheral classification elements, thus enabling increased precision in the generated count values.

[0014] According to one embodiment, the motion values ​​provided by the peripheral classification elements each describe incremental motion segments of the cyclic partial movements of the respective body parts on which the peripheral classification elements are arranged, and wherein determining the count value includes: Selecting the peripheral classification elements whose provided peripheral classification value matches the classification value of the central classification unit; Summing up the motion values ​​provided by the peripheral classification elements at different times and generating a cumulative motion value for at least one selected peripheral classification element; Determining an average motion value based on the cumulative motion values ​​of the selected peripheral classification elements, if the at least one cumulative motion value of the at least one selected peripheral classification element reaches or exceeds a value of one complete cycle of the cyclic partial motion; and Increasing the count value by one whenever the average movement value reaches or exceeds a value of a predefined part of a complete cycle of cyclic movement.

[0015] This allows for the technical advantage of increased precision in the count value. To achieve this, the peripheral classification elements are first selected whose peripheral classification values ​​match the classification values ​​of the central classification unit.

[0016] Therefore, only the motion values ​​of the peripheral classification elements that provided the correct classification of the motion are considered. The motion values ​​provided by the multiple peripheral classification elements represent segments of cyclical partial movements of the person's movement.

[0017] The motion values ​​provided at different times by the peripheral classification elements are cumulatively added up until a cumulative motion value of a peripheral classification element describes a complete cycle of the cyclic partial motion.

[0018] Based on this, an average movement value is determined from all movement values ​​of the selected peripheral classification elements.

[0019] Once the average movement value of all movement values ​​of the selected peripheral classification elements describes a complete cycle of cyclic movement, the counter is incremented by 1. This allows for a highly precise determination of the cyclic movement count.

[0020] Firstly, only the peripheral classification elements are considered in the calculation of the count value. Secondly, the various partial movements of the different body parts are also taken into account in the average movement value.

[0021] According to one embodiment, the method further comprises: Determining a success score for a peripheral classification element if the peripheral classification score provided by the respective peripheral classification element matches the classification score determined by the central classification unit; and Evaluating the performance of the majority of peripheral classification elements by the central classification unit based on the success values.

[0022] This allows for the technical advantage of determining the classification performance of individual peripheral classification elements. The resulting performance can then be displayed to the user.

[0023] Alternatively or additionally, performance can be taken into account in further classification steps by no longer considering poorly performing peripheral classification elements in subsequent steps.

[0024] According to one embodiment, determining the count value further comprises: determining a movement speed of the cyclic partial movements determined by the peripheral classification elements based on the movement values ​​provided by the peripheral classification elements and based on timestamps provided by the peripheral classification elements for the respective movement values, and generating movement values ​​by the central classification unit, wherein the timestamps define times at which the movement values ​​were determined by the peripheral classification elements.

[0025] This offers the technical advantage that, based on the movement values ​​of the various peripheral classification elements, a movement speed of the cyclic sub-movements can be determined. This can then be displayed to the user as additional information.

[0026] According to one embodiment, the peripheral classification values ​​and / or the motion values ​​of a peripheral classification element of the plurality of peripheral classification elements are disregarded for determining the classification value and / or for determining the count value if a time interval between peripheral classification values ​​and / or motion values ​​provided successively by the same peripheral classification element exceeds a predefined limit.

[0027] This achieves the technical advantage of further refining the determination of the classification value and / or the count value. Peripheral classification elements that have not transmitted new classification data to the central classification unit for a predetermined period are no longer considered in the further determination of the classification or count value, and the peripheral classification values ​​or movement values ​​already transmitted are disregarded in subsequent steps.

[0028] This allows faulty peripheral classification elements or peripheral classification elements located at body parts that do not perform cyclic movements over time to be excluded from the motion classification.

[0029] According to one embodiment, the method further comprises: Determining a pause in the movement by the central classification unit if the number of peripheral classification elements that have provided a peripheral classification value matching the classification value determined by the central classification unit falls below the predefined number and the time interval between peripheral classification values ​​provided successively by at least one peripheral classification element reaches or falls below the predefined time interval.

[0030] This allows for the technical advantage of precisely detecting pauses in the user's movement. These pauses are detected as soon as fewer than the predefined number of peripheral classification elements provide a peripheral classification value that matches the classification value of the central classification unit, but simultaneously, the peripheral classification elements provide classification data to the central classification unit at shorter intervals than the predefined time interval.

[0031] The predefined time span describes a maximum time span that may elapse between the provision by a peripheral classification element of two consecutive classification data points before the respective peripheral classification element is considered inactive.

[0032] This means that the peripheral classification elements continue to provide classification data at intervals shorter than the predefined time span, which in turn suggests that the motion classification system is still operational.

[0033] By identifying the pause in movement, the previously generated classification and count values ​​are retained, and the movement classification system waits for the user to resume movement. A complete system reset does not occur, and the process can continue with the previously generated values ​​when movement resumes.

[0034] According to one embodiment, the method further comprises: Determine that the classification system is in an idle state if the number of peripheral classification elements that have provided a peripheral classification value matching the classification value determined by the central classification unit falls below the predefined number and the time interval between peripheral classification values ​​provided successively by at least one peripheral classification element exceeds the predefined time interval.

[0035] This allows for the technical advantage of providing a precise determination of the idle state of the motion classification system.

[0036] This occurs when the number of peripheral classification elements providing a peripheral classification value that matches the classification value of the classification unit falls below the predefined number, and a longer period of time than the predefined time has elapsed since the peripheral classification elements last provided classification data. This indicates that the system is in an idle state.

[0037] According to one embodiment, the method further comprises: Resetting the classification value and / or the count value and / or the speed value and / or the success values ​​by the central classification unit if the idle state of the classification system has been determined.

[0038] This allows the technical advantage that by resetting the aforementioned values ​​if the classification system is in idle mode, the motion classification system can create a precise classification of the motion upon reuse without affecting the previous classification.

[0039] According to one embodiment, the classified movement is one from the following list: walking, running, hiking, mountaineering, swimming, cross-country skiing, cycling, and wherein the count value relates to a cyclic partial movement from the following list: step, swimming arm stroke, swimming leg kick, cycling crank revolution.

[0040] This allows the technical advantage to be achieved that the inventive method can classify a wide variety of movements with cyclic partial movements.

[0041] According to one aspect, a motion classification system is provided with a central classification unit and a plurality of peripheral classification elements, wherein the peripheral classification elements each comprise at least one motion sensor, and wherein the motion classification system is configured to perform the method for classifying a motion according to one of the preceding embodiments.

[0042] This allows the technical advantage to be achieved that an improved motion classification system is provided, which is set up to carry out the procedure for classifying a motion with the aforementioned technical advantages.

[0043] According to one embodiment, the peripheral classification elements and / or the central classification unit are designed as wearables.

[0044] This offers the technical advantage that the classification system can easily be worn by one person, and thus the person's movements can be classified using the movement classification system.

[0045] According to one aspect, a computing unit is provided which is set up to execute the procedure for classifying a movement according to one of the preceding embodiments.

[0046] According to one aspect, a computer program product is comprehensively provided with instructions which, when the program is executed by a data processing unit, cause it to perform the method for classifying a movement according to one of the preceding embodiments.

[0047] Embodiments of the invention are described with reference to the following figures. The figures show: Fig. 1 a schematic representation of a motion classification system according to one embodiment; Fig. 2 a flowchart of a method for classifying a movement according to an embodiment; Fig. 3 a further flowchart of the procedure for classifying a movement according to a further embodiment; Fig. 4. A further flowchart of the procedure for classifying a movement according to a further embodiment; Fig. 5 a further flowchart of the procedure for classifying a movement according to a further embodiment; Fig. 6. A further flowchart of the procedure for classifying a movement according to a further embodiment; and Fig. 7 A schematic representation of a computer program product.

[0048] Fig. Figure 1 shows a schematic representation of a motion classification system 200 according to one embodiment.

[0049] In Fig. Figure 1 shows a user 300 with a motion classification system 200 according to the invention. In the embodiment shown, the motion classification system 200 comprises four peripheral classification elements 201, each positioned on the four extremities of the person 300.

[0050] Furthermore, the motion classification system 200 includes a central classification unit 203, which in the embodiment shown is positioned on the torso of person 300.

[0051] The multiple peripheral classification elements 201 each include at least one motion sensor 223, via which the movements of the person 300 can be detected. The motion sensors 223 can be configured, for example, as accelerometers, gyroscopes, or other motion sensors known from the prior art.

[0052] The peripheral classification elements 201 are set up via the sensor values ​​of the motion sensors 223 to independently classify the movement of the person 300 and to generate peripheral classification values ​​207.

[0053] The peripheral classification values ​​207 describe the classification of the movement of person 300, which was independently generated by the respective peripheral classification element 201.

[0054] The various peripheral classification elements 201 are connected to the central classification unit 203 via data technology and send classification data 205, comprising at least the peripheral classification values ​​207, to the central classification unit 203.

[0055] Based on the peripheral classification values ​​207, the central classification unit 203 generates a classification value 209. The classification value 209 represents a classification of the movement of person 300 and is based on the peripheral classification values ​​207 of the peripheral classification elements 201.

[0056] According to one embodiment, the central classification unit 203 generates the classification value 209 by adopting the peripheral classification value 207 transmitted by the peripheral classification elements 201, provided that the number of peripheral classification elements 201 that have transmitted the same peripheral classification value 207 reaches or exceeds a predefined limit.

[0057] In the illustrated embodiment, the user 300 is depicted in a walking motion. Furthermore, the user 300 has a peripheral classification element 201 on each arm and each leg.

[0058] The central classification unit 203 can now be configured to adopt the peripheral classification value 205 as classification value 209, provided that at least two of the peripheral classification elements 201 provide the same peripheral classification value 207.

[0059] For example, if at least one peripheral classification element 201 on an arm and one peripheral classification element 201 on a leg of person 300 classifies the movement of person 300 as a walking movement, then the central classification unit 203 will also classify the movement of person 300 as walking.

[0060] According to one embodiment, in addition to the peripheral classification values ​​205, the peripheral classification elements 201 also transmit motion values ​​213 as part of the classification data 205 to the central classification unit 203.

[0061] Based on the movement values ​​213 of the peripheral classification elements 205, the central classification unit 203 generates a count value 215 of the movement of person 300.

[0062] The motion values ​​213 of the peripheral classification elements 201 describe movement segments of cyclic partial movements of the movement of person 300. In the embodiment shown, the cyclic partial movements describe the swinging of the arms or the stepping movements of the legs of person 300.

[0063] The count value 215, which is quantified by the central classification unit 203 based on the movement values ​​213, represents the successive execution of the cyclical partial movements. In the example shown, the count value 215 can, for instance, describe the number of steps taken during the running movement.

[0064] According to one embodiment, the peripheral classification elements 201 also transmit timestamps 221 as part of the classification data 205 to the central classification unit 203. The timestamps 221 describe the times at which the motion values ​​213 were recorded.

[0065] Based on the timestamps 221 and the movement values ​​213, the central classification unit 203 generates a speed value 219.

[0066] The velocity value 219 describes the execution speed of the cyclic partial movements, which are represented by the movement values ​​213 of the peripheral classification elements 201.

[0067] According to one embodiment, the central classification unit 203 further generates a success value 217. The success value 217 is generated for each peripheral classification element 201, each time the peripheral classification element 201 provides a peripheral classification value 207 that matches the classification value 209 generated by the central classification unit 203.

[0068] According to the invention, the individual peripheral classification elements 201 perform classifications of the movement throughout the movement of the user 300 and provide classification data 205 including at least the peripheral classification value 207 and optionally additionally the movement value 213 and the timestamp 221.

[0069] The peripheral classification elements 201 provide the classification data 205 to the central classification unit 203 in their own time-based sequence.

[0070] The individual peripheral classification elements 201 provide the classification data 205 in particular when a successful classification of the movement has been carried out.

[0071] At irregular intervals, the central classification unit 203 receives classification data 205 from the individual peripheral classification elements 201.

[0072] Each time a peripheral classification value 207 of a peripheral classification element 201 matches the previously generated classification value 209 of the central classification unit 203, a corresponding success value 217 is assigned to this peripheral classification element 201. The corresponding success values ​​217 can be used to assess the performance of the various peripheral classification elements 201.

[0073] In the embodiment shown, the motion classification system 200 further comprises a display unit 211. After generating the classification value 209 and / or the count value 215 and / or the speed value 219 and / or the success value 217, these values ​​are provided by the central classification unit 203 to the display unit 211 and can be displayed to the user 300 via this unit.

[0074] In the embodiment shown, the peripheral classification elements 201 and the central classification unit 203 are designed as wearables and can be attached to various parts of the user's body 300. The central classification unit 203 is implemented on a computing unit 225 of the motion classification system 200.

[0075] Alternatively, the central classification unit 203 can also be run on an external computing unit 225, for example a smartphone, tablet or PC.

[0076] In addition to the running movement shown here, the inventive method and the inventive movement classification system 200 can also be used to classify walking movements, hiking movements, mountaineering movements, swimming movements, cross-country skiing movements, cycling movements or other movements that include cyclic partial movements.

[0077] The count value 215 can represent a numerical value of a stepping movement, a swimming arm stroke movement, a wheel crank rotation movement, or other cyclic partial movements.

[0078] Fig. Figure 2 shows a flowchart of a method 100 for classifying a movement according to an embodiment.

[0079] To classify the movement of the user, in a first procedure step 101 the classification data 205 of the several peripheral classification elements 201 are received by the central classification unit 203.

[0080] In a further process step 103, the movement is classified by the central classification unit 203 based on the peripheral classification values ​​207 of the majority of peripheral classification elements 201 and the classification value 209 is generated.

[0081] In a further process step 105, the classification value 209 is provided by the central classification unit 203 to the display unit 211.

[0082] Fig. Figure 3 shows another flowchart of method 100 for classifying a movement according to a further embodiment.

[0083] The embodiment in Fig. 3 is based on the embodiment in Fig. 2 and includes all the procedural steps described therein.

[0084] In the embodiment shown, the classification data 205 provided by the peripheral classification elements 201 include, in addition to the parallel peripheral classification values ​​207, the motion values ​​213.

[0085] In a process step 107, the count value 215 is generated by the central classification unit 203 based on the movement values ​​213 of the peripheral classification elements 201.

[0086] In a further process step 111, the motion values ​​213 provided by the peripheral classification elements 201 at different times are added up and a cumulative motion value 213 is determined for at least one selected peripheral classification element 201. θi,k=θi,k−1+Δθi,k

[0087] Here, θ i,k the k-th motion value 213 of the i-th peripheral classification element 201, θ i,k-1 the (k-1)th motion value 213 of the i-th peripheral classification element 201 and Δθ i,k the change in motion from the (k-1)-th motion value 213 to the immediately following k-th motion value 213, where: Δθi=Δθi+dθi dθi=max(P,(θi,k−θi,k−1))

[0088] For this purpose, in a process step 109, the peripheral classification elements 201 are selected whose provided peripheral classification value 207 matches the classification value 209 of the central classification unit 203.

[0089] The movement values ​​213 of the peripheral classification elements 201 describe cyclic movements of the body parts on which the peripheral classification elements 201 are positioned. The movement values ​​213 can describe incremental segments of these cyclic movements. For example, the peripheral classification elements 201 can be configured to record a predefined number of movement values ​​213 per full cycle of the cyclic movement.

[0090] The motion values ​​213 can be expressed in radians, where one complete cycle is defined as 2π. The motion value can also be expressed as a percentage or degrees.

[0091] The motion values ​​213 can also include phase information. This phase information allows the movements of the individual body parts, on which the respective peripheral classification elements 201 are located, to be related to each other.

[0092] For example, it can be determined whether movements are performed in phase or out of phase with each other. For example, when walking or running, the swinging motion of the right arm with the left leg and of the left arm with the right leg can be detected.

[0093] In process step 109, the peripheral classification elements 201 are selected, whose motion values ​​213 describe such movements executed in phase.

[0094] In a further process step 113, an average movement value is determined based on the cumulative movement values ​​213 of the selected peripheral classification elements 201, if the at least one cumulative movement value of the at least one selected peripheral classification element 201 reaches or exceeds a value of a complete cycle of the cyclic partial movement.

[0095] The average movement value is calculated as follows: a weighted average over a set of peripheral classification elements 201: Δθ¯=∑i∈IωiΔθi where Δθ is the average movement value, Δθ i the cumulative motion value 213 of the i-th peripheral classification element 201, and ω iThe weight value associated with the i-th peripheral classification element 201. Set I is a set of all peripheral classification elements 201 used to calculate the average movement value. For this purpose, for example, primarily peripheral classification elements 201 with high performance can be selected. I={i:ai=m,Δθi>c∗max(Δθ)} where a i Peripheral classification value 207 of the i-th peripheral classification element 201, m the classification value 209 of the central classification unit 203, Δθ i the cumulative motion value 213 of the i-th peripheral classification element 201, and Δθ a vector representation of all cumulative motion values ​​213 of the selected peripheral classification elements 201. The weighting value ω i can be scaled with the performance of the respective peripheral classification elements 201: ωi=1 / nI

[0096] Where n l represents the size of the quantity.

[0097] The movement values ​​213 of the peripheral classification elements 201 describe movement segments of the cyclic movements, in particular of the individual body parts of the user 300.

[0098] By summing the motion values ​​213 provided sequentially by the various peripheral classification elements 201, a predefined part of a complete cycle of the cyclic motion determined by the respective peripheral classification element 201 is reached for each selected peripheral classification element 201 after a certain number of sequentially provided motion values ​​213 have been summed. The predefined part can be set to a quarter, half, or three-quarters of a cycle. Other values ​​are, of course, also possible.

[0099] The peripheral classification elements 201 can be configured such that the motion values ​​213 are recorded within the cycles of the cyclic movements in a predetermined number of incremental measurement steps.

[0100] For example, for the various peripheral classification elements 201, ten motion values ​​213 can be recorded for each cycle of the cyclic motion.

[0101] The ten motion values ​​213 are recorded sequentially at different times and transmitted to the central classification unit 203. After adding up the ten sequentially recorded motion values, a complete cycle of cyclic motion is achieved.

[0102] The average movement value is calculated based on all cumulative movement values ​​of the selected peripheral classification elements 201.

[0103] Since current movement values ​​213 of the peripheral classification elements 201 are constantly provided during ongoing movement, and the cumulative movement values ​​213 of the respective peripheral classification elements 201 increase accordingly over time, the average movement value will also assume a constantly larger value over time.

[0104] In a further process step 115, the count value 215 is subsequently increased by a numerical value 1 each time the average movement value reaches or exceeds a predefined part, i.e. a multiple, of a complete cycle of the cyclic movement.

[0105] The peripheral classification elements 201 selected for calculating the count value 215 can change over time depending on the peripheral classification values ​​207 provided accordingly; in particular, the number of selected peripheral classification elements 201 can vary over time based on the peripheral classification values ​​207 provided.

[0106] By calculating the average movement value, a precise determination of the count value 215 can thus be achieved.

[0107] Fig. Figure 4 shows another flowchart of method 100 for classifying a movement according to a further embodiment.

[0108] The embodiment in Fig. 4 is based on the embodiment in Fig. 2 and includes all the procedural steps described therein.

[0109] In the embodiment shown, in a process step 117 the success values ​​217 for the peripheral classification elements 201 are determined if the peripheral classification values ​​207 provided by the respective peripheral classification elements 201 match the classification values ​​209 determined by the central classification unit 203.

[0110] Based on the success values ​​217, feedback can be provided. i calculate: fi = expected success

[0111] Where si is the success value 217 of the i-th peripheral classification element 201 and where the expected success can be determined taking into account the peripheral classification element 201 with the highest success values.

[0112] In a further process step 119, the performance of the majority of peripheral classification elements 201 is evaluated by the central classification unit 203 based on the success values ​​217.

[0113] With a higher number of success values ​​217, the respective peripheral classification element 201 receives a higher performance value, and with a lower number of achieved success values ​​217, a correspondingly lower performance value.

[0114] Fig. Figure 5 shows another flowchart of method 100 for classifying a movement according to a further embodiment.

[0115] The embodiment in Fig. 5 is based on the embodiment in Fig. 3 and includes all the process steps described therein. In the embodiment shown, in a process step 121, the velocity value 219 of the cyclic motion is determined by the central classification unit 203 based on the motion values ​​213 and the timestamps 221.

[0116] The corresponding motion values ​​213 and / or speed values ​​219 can be provided in process step 105 of the display unit 211.

[0117] Fig. Figure 6 shows another flowchart of method 100 for classifying a movement according to a further embodiment.

[0118] The embodiment in Fig. 6 is based on the embodiment in Fig. 2 and includes all the procedural steps described therein.

[0119] In a process step 123, a pause in the movement of the user person 300 is determined if the number of peripheral classification elements 201, whose peripheral classification values ​​207 match the classification value 209 of the central classification unit 203, falls below the predefined number, and if the time interval between the peripheral classification values ​​207 provided successively reaches or falls below the predefined time interval.

[0120] In a process step 125, the idle state of the motion classification system 200 is determined by the central classification unit 201 if, in turn, the number of peripheral classification elements 201 that provide a peripheral classification value 207 that matches the classification value 209 is less than the predefined number and if the time interval between peripheral classification values ​​207 provided immediately one after the other exceeds the predefined time interval.

[0121] If the predefined time period is exceeded, it is assumed that no movement of person 300 has been detected by the movement classification system 200 for too long a period of time to be explained by a pause between movements of person 300.

[0122] If the last transmission of peripheral classification values ​​207 occurred longer than the predefined time period, this is instead identified with the idle state of the motion classification system 200.

[0123] In a further process step 127, the classification value 209 and / or the count value 215 and / or the speed value 219 and / or the success values ​​217, which were generated during the classification of the earlier movement, are reset by the central classification unit 203 if the idle state of the movement classification system 200 has been determined.

[0124] The embodiments of method 100 of Fig. 2 to 6 can also be combined with each other in ways other than those described above.

[0125] Fig.Figure 7 shows a schematic representation of a computer program product 400, comprising instructions which, when the program is executed by a data processing unit, cause it to perform the procedure 100 for classifying a movement.

[0126] In the embodiment shown, the computer program product 400 is stored on a storage medium 401. The storage medium 401 can be any storage medium known from the prior art.

Claims

[1] Method (100) for classifying a movement by means of a movement classification system (200) with a plurality of peripheral classification elements (201) and a central classification unit (203), wherein the peripheral classification elements (201) are arranged on different body parts (301) of a person (300) and each classify the movement of the person (300) based on sensor data, comprising: Receiving (101) classification data (205) of the plurality of peripheral classification elements (201) by the central classification unit (203), wherein the classification data (205) each comprise at least one peripheral classification value (207); Classifying (103) the movement and generating a classification value (209) by the central classification unit (203) based on the peripheral classification values ​​(207) of the plurality of peripheral classification elements (201); and Output (105) of the classification value (209) by the central classification unit (203) to a display unit (211). [2] Method (100) according to claim 1, wherein the classification value (209) determined by the central classification unit (203) corresponds to one of the peripheral classification values ​​(207) provided by the plurality of peripheral classification elements (201), if the respective peripheral classification value (207) was provided by at least a predefined number of peripheral classification elements (201). [3] Method (100) according to claim 1 or 2, wherein the classification data (205) each further comprise at least one movement value (213), and wherein the method (100) further comprises: Determining (107) a count value (215) of cyclic partial movements of the motion based on the movement values ​​(213) of the plurality of peripheral classification elements (201) by the central classification unit (203); and Output (105) of the count value (215) by the central classification unit (203) to the display unit (211). [4] Method (100) according to claim 3, wherein the motion values ​​(213) provided by the peripheral classification elements (201) each describe incremental motion segments of the cyclic partial movements of the respective body parts (301) on which the peripheral classification elements (201) are arranged, and wherein determining (107) the count value (215) comprises: Selecting (109) the peripheral classification elements (201) whose provided peripheral classification value (207) matches the classification value (209) of the central classification unit (203); Adding (111) the motion values ​​(213) provided by the peripheral classification elements (201) at different times and generating a cumulative motion value (213) for at least one selected peripheral classification element (201); Determine (113) an average motion value based on the cumulative motion values ​​(213) of the selected peripheral classification elements (201), if the at least one cumulative motion value (213) of the at least one selected peripheral classification element (201) reaches or exceeds a value of a complete cycle of the cyclic partial motion; and Increase (115) the count value (215) by one value “one” as soon as the average movement value reaches or exceeds a value of one complete cycle of cyclic movement. [5] Method (100) according to any one of the preceding claims, further comprising: Determine (117) a success value (217) for a peripheral classification element (201) if the peripheral classification value (207) provided by the respective peripheral classification element (201) matches the classification value (209) determined by the central classification unit (203); and Evaluating (119) the performance of the majority of peripheral classification elements (201) by the central classification unit (203) based on the success scores (217). [6] Method (100) according to any of the preceding claims, wherein the determination (107) further comprises: Determining (121) a velocity of the cyclic partial movements determined by the peripheral classification elements (201) based on the motion values ​​(213) provided by the peripheral classification elements (201) and based on timestamps (221) provided by the peripheral classification elements (201) for the respective motion values ​​(213) and generating velocity values ​​(219) by the central classification unit (203), wherein the timestamps (221) define times at which the motion values ​​(213) were determined by the peripheral classification elements (201). [7] Method (100) according to any of the preceding claims, wherein the peripheral classification values ​​(207) and / or the movement values ​​(213) of a peripheral classification element (201) of the plurality of peripheral classification elements (201) are disregarded for the determination of the classification value (209) and / or for the determination of the count value (215) if a time interval between peripheral classification values ​​(207) and / or movement values ​​(213) provided successively by the same peripheral classification element (201) exceeds a predefined limit. [8] Method (100) according to any one of the preceding claims, further comprising: Determining (123) a pause in the movement by the central classification unit (203) if the number of peripheral classification elements (201) that have provided a peripheral classification value (207) corresponding to the classification value (209) determined by the central classification unit (203) falls below the predefined number and the time interval between temporally successive at least one The peripheral classification element (201) provided peripheral classification values ​​(207) reach or fall below the predefined time period. [9] Method (100) according to any one of the preceding claims, further comprising: Determine (125) that the motion classification system (200) is in an idle state if the number of peripheral classification elements (201) that have provided a peripheral classification value (207) matching the classification value (209) determined by the central classification unit (203) falls below the predefined number and the time interval between sequentially determined by at least one The peripheral classification element (201) provided peripheral classification values ​​(207) exceeds the predefined time period. [10] Method (100) according to claim 9, further comprising: Resetting (127) the classification value (209) and / or the count value (215) and / or the speed value (219) and / or the success values ​​(217) by the central classification unit (203) if the idle state of the motion classification system (200) has been determined. [11] Method (100) according to any of the preceding claims, wherein the classified movement is one from the following list: walking, running, hiking, mountaineering, swimming, cross-country skiing, cycling, and wherein the count value (215) relates to a cyclic partial movement from the following list: step, swimming arm stroke, swimming leg kick, cycling crank revolution. [12] Motion classification system (200) comprising a central classification unit (203) and a plurality of peripheral classification elements (201), wherein the peripheral classification elements (201) each comprise at least one motion sensor (223), and wherein the motion classification system (200) is configured to perform the method (100) for classifying a motion according to any one of claims 1 to 11 above. [13] Motion classification system (200) according to claim 12, wherein the peripheral classification elements (201) and / or the central classification unit (203) are designed as wearables. [14] Computing unit (225) configured to perform the method (100) for classifying a motion according to any one of claims 1 to 11 above. [15] Computer program product (400) comprising instructions which, when the program is executed by a data processing unit, cause it to execute the method (100) for classifying a motion according to any one of the preceding claims 1 to 11.

Images